Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations give readOnlyHint=false and destructiveHint=false, and the description adds substantial context without contradicting them: it discloses that on an unknown block/field or a duplicate id the call is REFUSED with nothing written, that nothing is overwritten, and that a second link adds another path. That is exactly the non-obvious mutation behavior an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose in the first clause and packs prerequisites, refusals, optionals, and removal into a dense but tight block. Slightly long, but nearly every sentence carries operational value; not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no output schema, it covers what an agent needs: required inputs, existence/ownership prerequisites, refusal semantics, non-overwrite behavior, optional fields, and how to undo. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, but the description adds real meaning: it clarifies that fromFieldId omitted/null means the entire source block is the source (schema only says 'null if entire block'), and explains isPii default false plus how to flip it. That goes beyond the schema descriptions, though it doesn't add syntax details for every parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Traces ONE lineage link from a source field ... to a target field of an ERD entity') and even frames the business question it answers. It distinguishes the single-link scope from a whole-block source via the fromFieldId note, and the sibling delete_field_lineage covers removal, so the agent can route without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit prerequisites: blocks and fields must already exist and the field must belong to the named block, with the alternative (create first with add_data_source/add_entity/add_field) spelled out. It also names the removal path (delete_field_lineage) and the PII-flip path (mark_field_pii), leaving no ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.